CODEWITHSUNDEEP
pythonmachine-learningcomputer-visiondatasetmediapipe
Shivam bansal
Shivam bansal

Reputation: 9

Pose Correction Dataset

i wanted to work on pose correction system for my college final year project and needed a my own datasets. but i am not able to get the pose coordinates from the video into CSV file no matter what i try. I tried but there is no code or reference which can help me in it. So can anyone please tell how should i do it.

this is my code

import cv2
mp_drawing = mp.solutions.drawing_utils
mp_pose = mp.solutions.pose
cap = cv2.VideoCapture('C:/Users/lenovo/Downloads/pexels-julia-larson-6455077.mp4')
count=0
## Setup mediapipe instance
with mp_pose.Pose(min_detection_confidence=0.5, min_tracking_confidence=0.5) as pose:
    while cap.isOpened():
        ret, frame = cap.read()
        
        # Recolor image to RGB
        image = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
        image.flags.writeable = False
      
        # Make detection
        results = pose.process(image)
    
        # Recolor back to BGR
        image.flags.writeable = True
        image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
       
        # Extract landmarks
        try:
            landmarks = results.pose_landmarks.landmark
            LANDMARKS = landmarks[mp_pose.PoseLandmark.value]
            df = pd.DataFrame(LANDMARKS,columns)
            df.to_csv (r'C:/Users/lenovo/Downloads/dataset4.csv', index = False, header=True)
         
    
        except:
            pass
        
        
        # Render detections
        mp_drawing.draw_landmarks(image, results.pose_landmarks, mp_pose.POSE_CONNECTIONS,
                                mp_drawing.DrawingSpec(color=(245,117,66), thickness=2, circle_radius=2), 
                                mp_drawing.DrawingSpec(color=(245,66,230), thickness=2, circle_radius=2) 
                                 )               
        
        cv2.imshow('Mediapipe Feed', image)
        
        if cv2.waitKey(10) & 0xFF == ord('q'):
            break

    cap.release()
    cv2.destroyAllWindows()

Upvotes: 0

Views: 208

Answers (1)

YScharf
YScharf

Reputation: 2082

Try moving the lines saving the data to pandas DataFrame outside the while loop.

Create an empty list: landmarks_list

For each frame append landmarks to list.

Run the followning lines after the while has finished running over the video frames

df = pd.DataFrame(landmarks_list,columns)

df.to_csv (r'C:/Users/lenovo/Downloads/dataset4.csv', index = False, header=True)

Upvotes: 1

Related Questions